© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 6876
    Prev
    Next
    INDEX
    Explanations

    references to communication challenges and legal considerations in business environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ErrorException
    -0.16
    наÑĩала
    -0.16
    ÅĻi
    -0.15
    rios
    -0.14
    ë¶ĢíĦ°
    -0.14
    ision
    -0.13
    asal
    -0.13
     deÄŁil
    -0.13
    ï¼Ŀ
    -0.12
     ابتد
    -0.12
    POSITIVE LOGITS
     finally
    1.36
     Finally
    1.14
    finally
    1.13
    Finally
    1.09
     Lastly
    1.01
    Lastly
    1.01
    	finally
    0.79
    æľĢåIJİ
    0.70
     final
    0.70
    æľĢå¾Į
    0.64
    Activations Density 0.465%

    No Known Activations